The benefits of physical literacy for human flourishing: A machine learning–based exploration of adolescents DOI
Lin Jiabin, Zhu Shanshan,

Lai Xiaomei

и другие.

Applied Psychology Health and Well-Being, Год журнала: 2024, Номер 17(1)

Опубликована: Дек. 12, 2024

Physical literacy is a multidimensional concept considered fundamental for lifelong participation in physical activity. Although theories on the relationship between and human flourishing have been proposed, no comprehensive study of this adolescents has found. This aimed to predict variables (physical activity, health, mental academic performance) that correlate highly with adolescents' literacy. A sample 1004 primary middle school students was recruited six machine learning algorithms (decision tree, random forest, AdaBoost, CatBoost, LightGBM, k-nearest neighbours) were used. Random forest predicted health overall sample, an accuracy 53 percent, 86 per cent, 91.7 respectively; AdaBoost performance 98 cent. Overall sex subgroup predictions generally consistent, "sense self self-control" "self-expression communication others" as most significant variables. Family-type analysis results varied greatly, suggesting one-child families should focus "knowledge understanding," whereas multi-child others." Awareness underlying characteristics may yield greater benefits when intervening through

Язык: Английский

The benefits of physical literacy for human flourishing: A machine learning–based exploration of adolescents DOI
Lin Jiabin, Zhu Shanshan,

Lai Xiaomei

и другие.

Applied Psychology Health and Well-Being, Год журнала: 2024, Номер 17(1)

Опубликована: Дек. 12, 2024

Physical literacy is a multidimensional concept considered fundamental for lifelong participation in physical activity. Although theories on the relationship between and human flourishing have been proposed, no comprehensive study of this adolescents has found. This aimed to predict variables (physical activity, health, mental academic performance) that correlate highly with adolescents' literacy. A sample 1004 primary middle school students was recruited six machine learning algorithms (decision tree, random forest, AdaBoost, CatBoost, LightGBM, k-nearest neighbours) were used. Random forest predicted health overall sample, an accuracy 53 percent, 86 per cent, 91.7 respectively; AdaBoost performance 98 cent. Overall sex subgroup predictions generally consistent, "sense self self-control" "self-expression communication others" as most significant variables. Family-type analysis results varied greatly, suggesting one-child families should focus "knowledge understanding," whereas multi-child others." Awareness underlying characteristics may yield greater benefits when intervening through

Язык: Английский

Процитировано

2